Zilin Wang

Orcid: 0009-0003-6062-3015

Affiliations:
  • University of Oxford, Department of Computer Science, Oxford, UK
  • Tsinghua Shenzhen International Graduate School, Shenzhen, China
  • Tsinghua University, Beijing, China


According to our database1, Zilin Wang authored at least 16 papers between 2022 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
Procedural Generation of Algorithm Discovery Tasks in Machine Learning.
CoRR, March, 2026

Learning to Drive in New Cities Without Human Demonstrations.
CoRR, February, 2026

2025
Rethinking the Role of Dynamic Sparse Training for Scalable Deep Reinforcement Learning.
CoRR, October, 2025

HyperVLA: Efficient Inference in Vision-Language-Action Models via Hypernetworks.
CoRR, October, 2025

How Should We Meta-Learn Reinforcement Learning Algorithms?
CoRR, July, 2025

Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

Discrete Flow Matching is a Surprisingly Effective Post-training Method to Address Compound Error in Autoregressive Models.
Proceedings of the 6th ACM International Conference on AI in Finance, 2025

2024
Normalization Enhances Generalization in Visual Reinforcement Learning.
Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems, 2024

Explore 3D Dance Generation via Reward Model from Automatically-Ranked Demonstrations.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023
Learning Better with Less: Effective Augmentation for Sample-Efficient Visual Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

UnifiedGesture: A Unified Gesture Synthesis Model for Multiple Skeletons.
Proceedings of the 31st ACM International Conference on Multimedia, 2023

MC-SpEx: Towards Effective Speaker Extraction with Multi-Scale Interfusion and Conditional Speaker Modulation.
Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023

A Synthetic Corpus Generation Method for Neural Vocoder Training.
Proceedings of the IEEE International Conference on Acoustics, 2023

Inter-Subnet: Speech Enhancement with Subband Interaction.
Proceedings of the IEEE International Conference on Acoustics, 2023

2022
Speech Enhancement with Fullband-Subband Cross-Attention Network.
Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

FullSubNet+: Channel Attention Fullsubnet with Complex Spectrograms for Speech Enhancement.
Proceedings of the IEEE International Conference on Acoustics, 2022


  Loading...